ppo-Huggy / run_logs /timers.json
kmpartner's picture
Huggy
4458964 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.3980125188827515,
"min": 1.3980125188827515,
"max": 1.4273619651794434,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69500.796875,
"min": 67816.59375,
"max": 77972.5703125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 114.0552995391705,
"min": 93.4188679245283,
"max": 406.8455284552846,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49500.0,
"min": 48900.0,
"max": 50242.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999948.0,
"min": 49769.0,
"max": 1999948.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999948.0,
"min": 49769.0,
"max": 1999948.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3253443241119385,
"min": 0.05504629388451576,
"max": 2.3744406700134277,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1009.1994018554688,
"min": 6.7156476974487305,
"max": 1246.524169921875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.5451766690625575,
"min": 1.7420632299341139,
"max": 3.8780244669225734,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1538.6066743731499,
"min": 212.5317140519619,
"max": 1963.1483684778214,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.5451766690625575,
"min": 1.7420632299341139,
"max": 3.8780244669225734,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1538.6066743731499,
"min": 212.5317140519619,
"max": 1963.1483684778214,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016369779840331628,
"min": 0.012754937036192536,
"max": 0.020591897812684893,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04910933952099489,
"min": 0.026444657350657506,
"max": 0.06177569343805468,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04247539813319842,
"min": 0.021769489627331495,
"max": 0.06540821293989817,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.12742619439959527,
"min": 0.04353897925466299,
"max": 0.1962246388196945,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.1003489665833276e-06,
"min": 3.1003489665833276e-06,
"max": 0.00029534827655057494,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.301046899749983e-06,
"min": 9.301046899749983e-06,
"max": 0.0008441596686134501,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10103341666666667,
"min": 0.10103341666666667,
"max": 0.19844942499999996,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30310025,
"min": 0.20720319999999998,
"max": 0.5813865500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.156749166666658e-05,
"min": 6.156749166666658e-05,
"max": 0.0049226263075,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00018470247499999975,
"min": 0.00018470247499999975,
"max": 0.014071188844999999,
"count": 40
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 40
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1714706810",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1714709104"
},
"total": 2293.701845384,
"count": 1,
"self": 0.49752742600048805,
"children": {
"run_training.setup": {
"total": 0.06062906199997542,
"count": 1,
"self": 0.06062906199997542
},
"TrainerController.start_learning": {
"total": 2293.1436888959997,
"count": 1,
"self": 3.994509159971585,
"children": {
"TrainerController._reset_env": {
"total": 2.9006886529999747,
"count": 1,
"self": 2.9006886529999747
},
"TrainerController.advance": {
"total": 2286.1210373220283,
"count": 231140,
"self": 4.387544542841624,
"children": {
"env_step": {
"total": 1817.0526706740975,
"count": 231140,
"self": 1502.7961896411473,
"children": {
"SubprocessEnvManager._take_step": {
"total": 311.6029703199722,
"count": 231140,
"self": 16.966715274113312,
"children": {
"TorchPolicy.evaluate": {
"total": 294.6362550458589,
"count": 222976,
"self": 294.6362550458589
}
}
},
"workers": {
"total": 2.6535107129780044,
"count": 231140,
"self": 0.0,
"children": {
"worker_root": {
"total": 2286.3306066889386,
"count": 231140,
"is_parallel": true,
"self": 1069.8057151268804,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008313200000884535,
"count": 1,
"is_parallel": true,
"self": 0.00019539000004442642,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006359300000440271,
"count": 2,
"is_parallel": true,
"self": 0.0006359300000440271
}
}
},
"UnityEnvironment.step": {
"total": 0.07531151099999533,
"count": 1,
"is_parallel": true,
"self": 0.00037894299998697534,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019896699996024836,
"count": 1,
"is_parallel": true,
"self": 0.00019896699996024836
},
"communicator.exchange": {
"total": 0.07396083200001158,
"count": 1,
"is_parallel": true,
"self": 0.07396083200001158
},
"steps_from_proto": {
"total": 0.0007727690000365328,
"count": 1,
"is_parallel": true,
"self": 0.00020608400006949523,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005666849999670376,
"count": 2,
"is_parallel": true,
"self": 0.0005666849999670376
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1216.5248915620582,
"count": 231139,
"is_parallel": true,
"self": 37.81067612399988,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 80.13638995098097,
"count": 231139,
"is_parallel": true,
"self": 80.13638995098097
},
"communicator.exchange": {
"total": 1010.7980440871381,
"count": 231139,
"is_parallel": true,
"self": 1010.7980440871381
},
"steps_from_proto": {
"total": 87.77978139993934,
"count": 231139,
"is_parallel": true,
"self": 30.902002450073383,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.877778949865956,
"count": 462278,
"is_parallel": true,
"self": 56.877778949865956
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 464.6808221050892,
"count": 231140,
"self": 6.183949479037551,
"children": {
"process_trajectory": {
"total": 141.78492154305172,
"count": 231140,
"self": 140.44284331105246,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3420782319992668,
"count": 10,
"self": 1.3420782319992668
}
}
},
"_update_policy": {
"total": 316.7119510829999,
"count": 97,
"self": 253.9067135999942,
"children": {
"TorchPPOOptimizer.update": {
"total": 62.805237483005726,
"count": 2910,
"self": 62.805237483005726
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.170000000973232e-07,
"count": 1,
"self": 8.170000000973232e-07
},
"TrainerController._save_models": {
"total": 0.12745294399974227,
"count": 1,
"self": 0.0037550909996753035,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12369785300006697,
"count": 1,
"self": 0.12369785300006697
}
}
}
}
}
}
}